Skip to content

docs: fix broken r1 link & update bedrock model table #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
FortiShield wants to merge 4 commits into
base: main
Choose a base branch
from
Open

docs: fix broken r1 link & update bedrock model table #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3108e66
docs: fix broken r1 link
FortiShield Mar 12, 2025
d18aa8e
docs: update bedrock model table
FortiShield Mar 12, 2025
4cb3f90
docs: update bedrock model table
FortiShield Mar 12, 2025
feb4bfa
init commit
FortiShield Mar 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/cuddly-kings-give.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
'@ai-toolkit/codemod': patch
---

feat (packages/codemod): Set up package for automated migrations.
2 changes: 1 addition & 1 deletion content/docs/02-guides/25-r1.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,7 +121,7 @@ You can use DeepSeek R1 with the AI TOOLKIT through various providers. Here's a
| [Azure](/providers/ai-toolkit-providers/azure) | [`DeepSeek-R1`](https://ai.azure.com/explore/models/DeepSeek-R1/version/1/registry/azureml-deepseek#code-samples) | Requires Middleware |
| [Together AI](/providers/ai-toolkit-providers/togetherai) | [`deepseek-ai/DeepSeek-R1`](https://www.together.ai/models/deepseek-r1) | Requires Middleware |
| [FriendliAI](/providers/community-providers/friendliai) | [`deepseek-r1`](https://huggingface.co/deepseek-ai/DeepSeek-R1) | Requires Middleware |
| [LangDB](/providers/ai-toolkit-providers/langdb) | [`deepseek/deepseek-reasoner`](https://docs.langdb.ai/guides/deepseek) | Requires Middleware |
| [LangDB](/providers/community-providers/langdb) | [`deepseek/deepseek-reasoner`](https://docs.langdb.ai/guides/deepseek) | Requires Middleware |

### Building Interactive Interfaces

Expand Down
6 changes: 5 additions & 1 deletion content/providers/01-ai-toolkit-providers/08-amazon-bedrock.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -350,6 +350,9 @@ on how to integrate reasoning into your chatbot.
| ------------------------------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
| `amazon.titan-tg1-large` | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `amazon.titan-text-express-v1` | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `amazon.nova-micro-v1:0` | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `amazon.nova-lite-v1:0` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `amazon.nova-pro-v1:0` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
Comment on lines +353 to +355
Copy link
Copy Markdown

@coderabbitai coderabbitai bot Mar 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Verification agent

🧩 Analysis chain

New Amazon Nova Model Entries

The table now includes new rows for:

  • amazon.nova-micro-v1:0
  • amazon.nova-lite-v1:0
  • amazon.nova-pro-v1:0

Each row displays capability indicators (using <Cross size={18} /> and <Check size={18} />) that denote the feature support for image input, object generation, tool usage, and tool streaming. Please confirm that these indicators accurately reflect each model’s capabilities according to the latest Amazon Bedrock documentation.

I'll now run a web search query to verify that the capability indicators (using <Cross size={18} /> and <Check size={18} />) accurately reflect the latest Amazon Bedrock documentation for the new Amazon Nova models.

Once we have the results from this search, we'll be able to confirm whether the indicators in the table are correct and proceed to update the review comment accordingly.

🌐 Web query:

Amazon Bedrock documentation "amazon.nova-micro-v1:0" "amazon.nova-lite-v1:0" "amazon.nova-pro-v1:0" capabilities image input object generation tool usage tool streaming

💡 Result:

Amazon Bedrock's Nova model family (Micro, Lite, Pro) offers advanced multimodal capabilities through three distinct model IDs: amazon.nova-micro-v1:0, amazon.nova-lite-v1:0, and amazon.nova-pro-v1:0. These models support sophisticated interactions through multiple modalities and tool integrations.

Core Capabilities

1. Vision Processing

  • Image & Video Analysis: Supports direct processing of visual inputs including JPEG, PNG images and video formats like MP4[4][12]
  • Multimodal Context: Understands relationships between text and visual elements in documents/images through unified processing pipelines[1][13]

2. Tool Integration

  • Function Calling: Native support for tool usage through API integrations[12]
  • Streaming Tool Execution: Combines real-time generation with tool invocation using ConverseStream API[7][12]
# Example tool usage with boto3
response = client.converse(
    modelId="us.amazon.nova-pro-v1:0",
    messages=[{"role": "user", "content": [{"text": "Analyze this image"}]}],
    tools=[tool_definition]  # External tool schema
)

Model Comparison

Feature Nova Micro Nova Lite Nova Pro
Max Input Resolution 1080p 4K 8K
Tool Streaming Basic Advanced Enterprise
Concurrent Sessions 10 50 100+
Vision Frame Analysis 15fps 30fps 60fps

Streaming & Real-Time Features

  • Response Streaming: ConverseStream API enables incremental output delivery[7][12]
  • Hybrid Execution: Combines streaming text generation with parallel tool execution[12][19]
  • Latency Optimization: Sub-200ms response times for common vision tasks[16][18]

Security & Compliance

  • Input Validation: Built-in content moderation for images/videos[6][10]
  • Confidence Scoring: Visual grounding with hallucination mitigation[1][5]
  • Private Customization: Model fine-tuning without data retention[13][16]

These models integrate with Amazon Bedrock's ecosystem including Knowledge Bases for RAG workflows[9][19] and Data Automation for preprocessing multimodal content[1][5]. While focused on understanding rather than direct image generation (handled by Nova Canvas/Reel models[18]), they enable complex analysis of visual inputs combined with structured data operations.

Citations:

Action Required: Correct Capability Indicator for Amazon Nova Micro

Based on the latest Amazon Bedrock documentation, all Amazon Nova models—including amazon.nova-micro-v1:0—support image input. The current table incorrectly shows a <Cross size={18} /> for image input on the micro model. Please update this so that amazon.nova-micro-v1:0 uses <Check size={18} /> for image input, ensuring consistency with its documented multimodal (image processing) capability.

  • File: content/providers/01-ai-toolkit-providers/08-amazon-bedrock.mdx (Lines 353-355)
  • Change Needed: For the amazon.nova-micro-v1:0 entry, replace <Cross size={18} /> with <Check size={18} /> in the image input column.

This adjustment will accurately reflect the capabilities as specified in the Amazon Bedrock documentation.

| `anthropic.claude-3-7-sonnet-20250219-v1:0` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `anthropic.claude-3-5-sonnet-20241022-v2:0` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `anthropic.claude-3-5-sonnet-20240620-v1:0` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
Expand All @@ -360,6 +363,7 @@ on how to integrate reasoning into your chatbot.
| `anthropic.claude-v2:1` | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `cohere.command-r-v1:0` | <Cross size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Cross size={18} /> |
| `cohere.command-r-plus-v1:0` | <Cross size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Cross size={18} /> |
| `deepseek.r1-v1:0` | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `meta.llama2-13b-chat-v1` | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `meta.llama2-70b-chat-v1` | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `meta.llama3-8b-instruct-v1:0` | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
Expand All @@ -378,7 +382,7 @@ on how to integrate reasoning into your chatbot.

<Note>
The table above lists popular models. Please see the [Amazon Bedrock
docs](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html#conversation-inference-supported-models-features)
docs](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-supported-models-features.html)
for a full list of available models. The table above lists popular models. You
can also pass any available provider model ID as a string if needed.
</Note>
Expand Down
2 changes: 1 addition & 1 deletion content/providers/03-community-providers/11-cloudflare-workers-ai.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ Then, setup an AI binding in your Cloudflare Workers project `wrangler.toml` fil

```bash filename="wrangler.toml"
[ai]
binding = "AI"
binding = "AI-TOOLKIT"
```

## Provider Instance
Expand Down
44 changes: 0 additions & 44 deletions packages/ai-toolkit/tsconfig.vitest-temp.json
View file
Open in desktop

This file was deleted.

2 changes: 1 addition & 1 deletion packages/codemod/src/test/__testfixtures__/rewrite-framework-imports-solid.input.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
// @ts-nocheck
import { useChat } from 'ai-toolkit/solid';
import { useChat } from 'ai-toolkit/solid';
Loading